Instrument equipment fault diagnosis method, device, electronic device and readable storage medium

Abstract

The present disclosure relates to the technical field of instrument equipment management and control, and discloses an instrument equipment fault diagnosis method, device, electronic device and readable storage medium; the method includes: obtaining the equipment operation data of multiple instrument equipment in the target site in real time; using the trained fault risk judgment model, processing the equipment operation data of multiple instrument equipment and the actual working condition data of the target site to obtain the fault risk existence result corresponding to each instrument equipment; for any target instrument equipment with fault risk, based on the trained fault diagnosis model, the equipment operation data of the target instrument equipment and the fault-related data, generating the target fault diagnosis result; wherein the fault-related data includes at least one of the following: operation log and maintenance record; the target fault diagnosis result includes the fault type, fault location and fault cause. Compared with the prior art, the present disclosure can realize the automatic diagnosis of instrument equipment faults, with fast diagnosis speed and high diagnosis accuracy.

Description

Technical Field

[0001] The present disclosure relates to the technical field of instrument equipment management and control, and in particular to an instrument equipment fault diagnosis method, device, electronic device and computer-readable storage medium. Background Art

[0002] During the operation of nuclear power plants, instrumentation equipment plays an important role in monitoring and providing feedback on key operating parameters. Its stability and reliability are directly related to the safe operation of nuclear power plants. Due to the particularity of the operating environment of nuclear power plants, instrumentation equipment often faces complex working conditions such as high temperature, high pressure, and high radiation, and is prone to failure. Therefore, how to accurately diagnose instrumentation equipment becomes particularly important.

[0003] Traditional fault diagnosis methods often rely on manual inspection and empirical judgment, which are slow and have low diagnostic accuracy. Therefore, it is urgent to solve this technical problem. Summary of the invention

[0004] In view of the above situation, the embodiments of the present disclosure provide an instrument equipment fault diagnosis method, device, electronic device and computer-readable storage medium, aiming to solve the above problems or at least partially solve the above problems.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for diagnosing a fault of an instrument device, the method comprising:

[0006] Obtain equipment operation data of multiple instruments and equipment in the target site in real time;

[0007] Using the trained fault risk judgment model, the equipment operation data of the multiple instrument equipment and the actual working condition data of the target site are processed to obtain the fault risk existence result corresponding to each instrument equipment;

[0008] For any target instrument equipment with a risk of failure, a target fault diagnosis result is generated based on a trained fault diagnosis model, the equipment operation data and fault-related data of the target instrument equipment; wherein the fault-related data includes at least one of the following: an operation log and a maintenance record; and the target fault diagnosis result includes the fault type, fault location and fault cause.

[0009] In a second aspect, the present disclosure also provides an instrument equipment fault diagnosis device, the device comprising:

[0010] An acquisition module is used to acquire the equipment operation data of multiple instrument equipment in the target site in real time;

[0011] A risk existence judgment module is used to process the equipment operation data of the plurality of instrument equipment and the actual working condition data of the target site by using the trained fault risk judgment model to obtain the fault risk existence result corresponding to each instrument equipment;

[0012] A fault diagnosis module is used to generate a target fault diagnosis result for any target instrument equipment with a risk of failure based on a trained fault diagnosis model, the equipment operation data of the target instrument equipment and fault-related data; wherein the fault-related data includes at least one of the following: an operation log and a maintenance record; and the target fault diagnosis result includes the fault type, fault location and fault cause.

[0013] In a third aspect, an embodiment of the present disclosure further provides an electronic device, comprising: a processor; and a memory arranged to store computer executable instructions, wherein when the executable instructions are executed, the processor executes the steps of the above-mentioned instrument equipment fault diagnosis method.

[0014] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes the steps of the above-mentioned instrument equipment fault diagnosis method.

[0015] By means of the above-mentioned technical scheme, the instrument equipment fault diagnosis method, device, electronic device and computer-readable storage medium provided by the embodiments of the present disclosure do not rely on the subjective experience of troubleshooting personnel compared with the prior art, but obtain the equipment operation data of multiple instrument equipment in the target site in real time by using the trained fault risk judgment model, process the equipment operation data of multiple instrument equipment and the actual operating condition data of the target site, and obtain the fault risk existence results corresponding to each instrument equipment; for any target instrument equipment with fault risk, generate the target fault diagnosis result based on the trained fault diagnosis model, the equipment operation data of the target instrument equipment and the fault-related data, thereby realizing the reasonable analysis and automatic diagnosis of the instrument equipment fault, with fast diagnosis speed and high diagnosis accuracy.

[0016] The above description is only an overview of the technical solution of the present disclosure. In order to more clearly understand the technical means of the present disclosure, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present disclosure more obvious and easy to understand, the specific implementation methods of the present disclosure are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure. In the drawings:

[0018] Figure 1 A schematic diagram of a flow chart of a method for diagnosing instrument equipment faults provided by an embodiment of the present disclosure is shown;

[0019] Figure 2 A schematic diagram showing the structure of an instrument equipment fault diagnosis device provided by an embodiment of the present disclosure is shown;

[0020] Figure 3 A schematic diagram showing the structure of an instrument equipment fault diagnosis device provided by another embodiment of the present disclosure is shown;

[0021] Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the technical solutions of the present disclosure will be clearly and completely described below in combination with the specific embodiments of the present disclosure and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure.

[0023] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such usage is interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the term "including" and its variants are to be interpreted as open-ended terms meaning "including but not limited to".

[0025] As mentioned above, the fault diagnosis methods in the prior art often rely on manual inspection and empirical judgment, which have slow diagnostic speed and low diagnostic accuracy. Based on this, the present invention proposes an instrument equipment fault diagnosis method, device, electronic device and computer-readable storage medium. The present disclosure is described in detail below through specific embodiments.

[0026] To facilitate understanding of this embodiment, a method for diagnosing instrument equipment faults disclosed in the embodiment of the present disclosure is first introduced in detail. The executor of the method for diagnosing instrument equipment faults provided in the embodiment of the present disclosure is generally a computer device with certain computing capabilities, and the computer device includes, for example: a terminal device or a server or other processing device, and the terminal device may be a user equipment (UE), a mobile device, a user terminal, a terminal, a personal digital assistant (PDA), etc. In some possible implementations, the method for diagnosing instrument equipment faults may be implemented by a processor calling computer-readable instructions stored in a memory.

[0027] Figure 1 The schematic diagram of the flow chart of the instrument equipment fault diagnosis method provided by the embodiment of the present disclosure is shown. Figure 1 It can be seen that the embodiment of the present disclosure at least includes steps S101 to S103:

[0028] Step S101: Acquire equipment operation data of multiple instrument equipment in a target site in real time.

[0029] First of all, it should be noted that the technical solutions provided in the embodiments of the present disclosure can be applied to a variety of scenarios, such as: nuclear power plants, oil refineries, chemical plants, steel plants, natural gas processing plants, etc., that is, the present disclosure does not limit the target site. Instrument equipment types include but are not limited to: pressure instruments, temperature instruments, flow meters, liquid level meters, radiation monitoring instruments, vibration meters, electric power meters, control instruments, water quality analysis instruments, speed meters, etc.

[0030] During implementation, for example, for multiple instrumentation equipment in a nuclear power plant, the sensor data installed in the instrumentation equipment can be collected at a certain frequency to obtain equipment operation data. For example, for a temperature instrument, the collected equipment operation data is a temperature sequence.

[0031] Step S102: using the trained fault risk judgment model, the equipment operation data of the plurality of instrument equipment and the actual working condition data of the target site are processed to obtain the fault risk existence result corresponding to each instrument equipment.

[0032] Here, the actual operating data includes, but is not limited to: process parameter data (such as temperature, concentration, reaction time, etc. of chemical reactions), environmental data (such as environmental factors such as temperature, humidity, and air pressure), energy consumption data (such as power and fuel consumption), production efficiency data (such as output, quality indicators, etc.), and safety monitoring data (such as radiation levels, concentrations of harmful gases, etc.). It is understandable that different target sites correspond to different actual operating data. For example, for a nuclear power plant, the actual operating data may be, for example, reactor parameters (such as reactor power, neutron flux, fuel temperature, etc.), coolant parameters (such as coolant temperature, pressure, flow, etc.), steam parameters (such as steam pressure, temperature, flow, etc.), generator parameters (such as generator power, voltage, current, etc.), safety system parameters (such as containment pressure, radioactive material monitoring data, etc.), equipment status parameters (such as operating status data of equipment such as pumps, valves, and pipelines), and environmental parameters (such as temperature, humidity, and radiation levels around the nuclear power plant).

[0033] The trained fault risk judgment model is used for classification tasks, and the output is the result of the presence / absence of fault risk. In specific implementation, for example, it can be generated based on models such as BP neural network (error back propagation neural network), RBF neural network (single hidden layer feedforward neural network), long short-term memory network, etc. The disclosed embodiment does not limit the model based on which the fault risk judgment model is generated.

[0034] Step S103: For any target instrument equipment with a fault risk, a target fault diagnosis result is generated based on a trained fault diagnosis model, the equipment operation data and fault-related data of the target instrument equipment, wherein the fault-related data includes at least one of the following: an operation log and a maintenance record; and the target fault diagnosis result includes the fault type, fault location and fault cause.

[0035] During implementation, the equipment operation data and fault-related data of the target instrument equipment can be preprocessed, such as denoising and normalization, to improve the quality and consistency of the data. The trained fault diagnosis model can extract features from the equipment operation data and fault-related data, extract key features related to the fault, such as the waveform, spectrum characteristics, statistical parameters, etc. of the signal, and then use these features to identify the fault mode.

[0036] from Figure 1It can be seen from the method shown that, compared with the prior art, the solution provided by the embodiment of the present disclosure does not rely on the subjective experience of troubleshooting personnel, but instead obtains the equipment operation data of multiple instrument equipment in the target site in real time; uses the trained fault risk judgment model to process the equipment operation data of multiple instrument equipment and the actual operating condition data of the target site to obtain the fault risk existence results corresponding to each instrument equipment; for any target instrument equipment with a fault risk, based on the trained fault diagnosis model, the equipment operation data of the target instrument equipment and the fault-related data, a target fault diagnosis result is generated, thereby achieving reasonable analysis and automatic diagnosis of instrument equipment faults, with fast diagnosis speed and high diagnosis accuracy.

[0037] Further, in order to better illustrate the process of the above instrument equipment fault diagnosis method, as a refinement and extension of the above embodiment, the embodiment of the present invention provides several optional embodiments, but is not limited thereto, which are specifically as follows:

[0038] In a possible implementation manner, the trained fault risk judgment model is generated according to the following method:

[0039] Step A1: obtaining a training set; wherein the characteristic data of the samples in the training set include sample equipment operation data and sample working condition data of multiple instrument equipment in the target site, and the label of the sample is whether there is a failure risk or not;

[0040] Step A2: inputting the characteristic data of each sample in the training set into the fault risk judgment model to be trained to obtain each fault risk prediction value;

[0041] Step A3: Calculate each loss value according to each of the fault risk prediction values, the corresponding sample labels, and a preset loss function;

[0042] Step A4: using the loss values, updating the parameters in the fault risk judgment model to be trained to obtain the trained fault risk judgment model.

[0043] During implementation, the feature data of the samples in the training set can be preprocessed first to eliminate possible noise, outliers or data drift problems, ensure the accuracy and reliability of the training data, and obtain the preprocessed samples. During specific implementation, the feature data in a sample can be input into the fault risk judgment model to be trained to obtain the corresponding fault risk prediction value; then, the preset loss function, such as the loss value of the mean square error, cross entropy loss function, etc., is calculated using the fault risk prediction value and the label data of the sample, and the parameters in the fault risk judgment model to be trained are updated using the loss value. Similarly, the remaining samples are used to update the parameters in the model. After obtaining a fault risk judgment model that meets the training requirements, the fault risk judgment model that meets the training requirements can be determined as the above-mentioned trained fault risk judgment model.

[0044] Among them, satisfying the training requirements may be: the function value of a preset loss function converges, or the training accuracy of the fault risk judgment model to be trained meets the preset requirements. The present disclosure does not make any specific limitation on satisfying the training requirements, which is subject to achievable.

[0045] In a possible implementation manner, for any target instrument device with a risk of failure, generating a target fault diagnosis result based on a trained fault diagnosis model, device operation data and fault-related data of the target instrument device includes:

[0046] Step S1031: using the trained fault diagnosis model, processing the equipment operation data and fault-related data of the target instrument equipment to obtain a fault mode recognition result;

[0047] Step S1032: Based on a preset first mapping relationship, using the acquired real-time operation data of the target instrument equipment and the fault mode recognition result, generate a fault type and a fault location; wherein the preset first mapping relationship represents the correspondence between the real-time operation data of the instrument equipment, the fault mode, and the fault type and the fault location;

[0048] Step S1033: Based on a preset second mapping relationship, determine the fault cause according to the fault type; wherein the preset second mapping relationship represents a corresponding relationship between the fault type and the fault cause.

[0049] During implementation, a suitable fault diagnosis algorithm can be selected according to the characteristics of the instrument equipment. For example, if the data of the instrument equipment presents a nonlinear and complex pattern, the random forest algorithm can be selected, and a trained fault diagnosis model can be obtained based on the training of the algorithm. Specifically, it can be generated according to the following method: obtain a training sample set; wherein the characteristic data of the samples in the training sample set include the historical equipment operation data and historical fault-related data of the target instrument equipment, and the label of the sample is the fault mode. Then, the model parameters of the initial random forest model are set, and the model parameters include the number of decision trees, and the number of decision trees is multiple; randomly extract elements from the training sample set as training samples; use the training samples to train the initial random forest model to obtain a trained fault diagnosis model.

[0050] The real-time operation data of the target instrument equipment refers to the data collected, measured and generated in real time during the operation of the instrument equipment. These data reflect the current working status, measurement values ​​and possible operation anomalies of the instrument equipment. For flow meters, real-time data may include but is not limited to the following types: flow value pressure value, temperature value, cumulative value (flow meters usually record the total cumulative amount of fluid passing through), status information (such as valve opening and closing status, battery power, signal quality, etc.), alarm information (when the instrument equipment detects an abnormality or exceeds the preset threshold, it will trigger an alarm information, such as low flow, high flow, abnormal pressure, etc.), timestamp, other parameters (such as density, viscosity, component analysis, etc.).

[0051] The first mapping relationship and the second mapping relationship can be set by the user according to actual needs, and the embodiments of the present disclosure are not limited to this. For example, the following Table 2 is a preset first mapping relationship. The following Table 2 is a preset second mapping relationship. The examples here are only illustrative and do not limit the embodiments of the present disclosure. During implementation, if the flow meter is subjected to fault mode identification, and the fault mode is obtained as the instrument reading presents a minimum value, and the real-time operating data of the target instrument equipment indicates that the instrument reading is abnormally small, then according to the following Table 1, it can be known that the fault type is a sensor fault, and the fault location is the sensor part. Then, according to the following Table 2, when the fault type is a sensor fault, the cause of the fault is sensor damage, dirt blockage, etc.

[0052] Table 1 Preset first mapping relationship

[0053] Real-time data Failure Mode Fault type Fault location The meter reading is abnormally small The instrument reading shows the minimum value Sensor failure Sensor part The meter reading is abnormally high The meter reading shows the maximum value Control system failure Control system part The meter reading fluctuates greatly Unstable meter readings Instrument performance issues Inside the instrument

[0054] Table 2 Preset second mapping relationship

[0055] Fault type Cause Sensor failure Sensor damage, dirt blockage, etc. Control system failure Control logic error, power supply problem, etc.

[0056] During implementation, after the fault mode is identified, the fault data can be further mined and analyzed. For example, by using causal reasoning, association rule mining and other methods, combined with the structure and working principle of the instrument equipment, the cause of the fault can be accurately located.

[0057] In actual application scenarios, after obtaining the target fault diagnosis results of the instrument equipment, an alarm signal can also be sent to the relevant operation and maintenance personnel to notify them to handle it. In specific implementation, for example, for fault A with fault location A1 and fault type A2, an alarm signal can be sent to the operation and maintenance personnel B1 closest to the fault location A1 to notify the operation and maintenance personnel B1 to handle it. An alarm signal can also be sent to the operation and maintenance personnel B2 who has repaired fault type A2 the most times to notify the operation and maintenance personnel B2 to handle it. In the present disclosure, in a possible implementation manner, the method further includes: for any target operation and maintenance personnel, determining target operation and maintenance selection data based on at least two of the following items: target operation and maintenance distance, target operation and maintenance times, and target abnormal operation and maintenance times; wherein the target operation and maintenance distance is determined based on the location data of the target fault instrument equipment and the location data of the target operation and maintenance personnel; the target operation and maintenance times is the total number of times the target operation and maintenance personnel performs operation and maintenance on the target fault type corresponding to the target fault instrument equipment; the target abnormal operation and maintenance times is the number of abnormal operation and maintenance processes performed by the target operation and maintenance personnel within a preset detection period; determining at least one target personnel based on each of the target operation and maintenance selection data; and sending an alarm signal to a terminal used by the at least one target personnel.

[0058] In this embodiment, for the target operation and maintenance distance, the target operation and maintenance distance is determined based on the location data of the target faulty instrument equipment and the location data of the target operation and maintenance personnel. For example, in a nuclear power plant, the detailed map and coordinate system of the nuclear power plant can be used to determine the location coordinates of the target faulty instrument equipment and the target operation and maintenance personnel; then the path planning algorithm is used to determine the shortest or most feasible walking path; then, according to the channel and area restrictions of the nuclear power plant, the calculated walking path is adjusted to finally obtain the target operation and maintenance distance. For the target number of abnormal operation and maintenance, for example, the moment when the target operation and maintenance personnel receives the alarm signal can be obtained and marked as the alarm moment, and the moment when the target operation and maintenance personnel starts the operation and maintenance processing can be obtained and marked as the operation and maintenance moment, and the interval between the operation and maintenance moment and the alarm moment can be marked as the preparation time; if the preparation time exceeds the preset preparation time threshold, the operation and maintenance process is marked as an abnormal operation and maintenance process.

[0059] In specific implementation, for any target operation and maintenance personnel, for example, the target operation and maintenance selection data can be determined based on the target operation and maintenance distance and the target operation and maintenance times. Specifically, the target operation and maintenance distance and the target operation and maintenance times can be weighted averaged to obtain the target operation and maintenance selection data. For another example, the target operation and maintenance selection data can be determined based on the target operation and maintenance distance, the target operation and maintenance times, and the target abnormal operation and maintenance times. Specifically, the target operation and maintenance selection data can be determined according to the following formula:

[0060]

[0061] Among them, XP is the target operation and maintenance selection data; XL is the target operation and maintenance distance; XS is the target operation and maintenance times; XR is the target abnormal operation and maintenance times, and a1, a2, and a3 are preset proportional coefficients, all of which are positive numbers and can be set according to actual needs. It can be understood that the larger the value of the target operation and maintenance selection data XP, the less suitable the corresponding operation and maintenance personnel are for the operation and maintenance processing of the instrument equipment at that time.

[0062] After obtaining the target operation and maintenance selection data of each target operation and maintenance personnel, one or more target personnel can be determined, and the number of target personnel can be set according to actual needs, which is not limited in this embodiment. Finally, an alarm signal can be sent to the terminal device used by each target personnel to notify each operation and maintenance personnel to handle the fault.

[0063] The disclosed embodiment determines the target operation and maintenance selection data according to at least two of the target operation and maintenance distance, the target operation and maintenance times, and the target abnormal operation and maintenance times, so that when selecting the target personnel to repair the fault, multiple factors such as distance, personnel maintenance level, and personnel's familiarity with the fault type can be considered, thereby ensuring the timeliness and effectiveness of fault handling.

[0064] In a possible implementation manner, the method further includes:

[0065] Step S104: calculating an index value of at least one fault evaluation index according to the acquired fault occurrence status data of the plurality of instrument devices within a preset period, and generating a fault risk signal according to the index value of the at least one fault evaluation index;

[0066] Step S105: Calculate the index value of at least one repair evaluation index according to the acquired occurrence time and elimination time of each fault, and generate a fault repair state signal according to the index value of the at least one repair evaluation index;

[0067] Step S106: If the fault repair status signal is a fault repair qualified signal, calculate the index value of at least one operation and maintenance evaluation index according to the acquired operation and maintenance monitoring data of each fault, and generate an operation and maintenance evaluation signal according to the index value of the at least one operation and maintenance evaluation index.

[0068] This embodiment can perform progressive and precise analysis on the operating performance, fault repair performance and operation and maintenance performance of the instrument equipment, which is conducive to the planning and adjustment of the instrument equipment management plan and has a high degree of intelligence.

[0069] During implementation, first, for step S104, the fault occurrence data here may be, for example, the fault types of all faults occurring in multiple instrumentation devices, the number of occurrences of each fault type, the occurrence time of each fault, etc. Fault evaluation indicators include: the number of fault types of non-easy-to-manage faults, the mean value of relative fault frequency, fault distribution data, and other indicators.

[0070] In one possible implementation, the fault occurrence status data includes: the fault types of all faults occurring in multiple instrument devices and the number of occurrences of each fault type. Each fault type can be marked as a non-easy-to-manage fault based on the number of occurrences of each fault type and the corresponding preset number of fault occurrences; if the number of fault types marked as non-easy-to-manage faults is greater than the preset number of non-easy-to-manage faults, a high-risk fault signal is generated; if the number of fault types marked as non-easy-to-manage faults is less than or equal to the preset number of non-easy-to-manage faults, a low-risk fault signal is generated.

[0071] In another possible implementation manner, the fault occurrence status data includes: the fault types of all faults occurring in the multiple instrument devices, the number of occurrences of each fault type, and the occurrence time of each fault; the step of calculating the index value of at least one fault evaluation index based on the acquired fault occurrence status data of the multiple instrument devices within a preset period, and generating a fault risk signal based on the index value of the at least one fault evaluation index includes:

[0072] Step S1041: marking each fault type as a non-manageable fault according to the number of occurrences of each fault type and the corresponding preset number of occurrences of each fault type;

[0073] Step S1042: if the number of fault types marked as non-easy-to-manage faults is greater than a preset number of non-easy-to-manage faults, a high-risk fault signal is generated;

[0074] Step S1043: if the number of fault types marked as non-easy-to-manage faults is less than or equal to the preset number of non-easy-to-manage faults, determining a mean value of the relative frequency of faults according to the number of occurrences and the corresponding preset number of occurrences of the faults;

[0075] Step S1044: determining the total number of fault occurrences in each target time period according to the occurrence time of each fault, and marking each target time period as a fault time period according to the preset total number of fault occurrences; determining fault distribution data according to the number of target time periods marked as fault time periods and the total number of target time periods;

[0076] Step S1045: performing weighted average on at least two of the number of fault types marked as non-easy-to-manage faults, the mean value of the relative frequency of the faults, and the fault distribution data to obtain a fault summary value;

[0077] Step S1046: Generate a fault risk signal according to the fault summary value and a preset summary threshold.

[0078] In this embodiment, each fault type can be marked as a non-easy-to-manage fault based on the number of occurrences of each fault type and the corresponding preset number of occurrences of the fault. For example, multiple instrument devices have M1 faults M within a preset period, the preset number of occurrences of the fault can be set according to the fault type, and the preset number of occurrences of the fault M corresponding to the fault is M2. If M1 is greater than M2, it indicates that the fault frequency of the fault M in the instrument device within the preset period is high, and the fault type of the fault M is marked as a non-easy-to-manage fault.

[0079] Then, the quantitative relationship between the number of fault types marked as non-easy-to-manage faults and the preset number of non-easy-to-manage faults can be determined, wherein the preset number of non-easy-to-manage faults can be set according to actual needs, and the present disclosure does not limit this. If the number of fault types marked as non-easy-to-manage faults is greater than the preset number of non-easy-to-manage faults, it indicates that the fault management difficulty for the instrument equipment within the preset period is relatively large, and the fault risk is relatively high, then a high-risk fault signal is generated. When the high-risk fault signal is obtained, the operation monitoring and fault management of the corresponding instrument equipment can be strengthened in the future to reduce the subsequent operation risk of the corresponding instrument equipment; if the number of fault types marked as non-easy-to-manage faults is less than or equal to the preset number of non-easy-to-manage faults, then the mean relative frequency of the faults can be determined based on the number of occurrences and the corresponding preset number of fault occurrences. Exemplarily, for the number of occurrences m1, the corresponding preset number of fault occurrences is m11, then m1 / m11 is determined as the relative frequency value of the fault, and by analogy, the relative frequency values ​​of the faults corresponding to the number of occurrences m2, m3, m4, etc. are m2 / m21, m3 / m31, and m4 / m41, respectively. Then, by calculating the average of m1 / m11, m2 / m21, m3 / m31, and m4 / m41, the mean of the relative frequency of faults can be obtained.

[0080] Then, the total number of faults occurring in each target period can be determined according to the occurrence time of each fault, and each target period can be marked as a fault period according to the preset total number of faults occurring; the fault distribution data can be determined according to the number of target periods marked as fault periods and the total number of target periods. Specifically, for example, the preset period can be divided into target period 1, target period 2, and target period 3, and the total number of faults occurring in target period 1, 11, 21, and 31 can be calculated. Here, the preset total number of faults occurring can be set according to actual needs, and this disclosure does not limit this. Then, the relationship between the preset total number of faults occurring and the total number of faults 11, 21, and 31 is determined respectively. If the total number of faults 11 and the total number of faults 21 are both greater than the preset total number of faults occurring, and the total number of faults 31 is less than the preset total number of faults occurring, the target period 1 and the target period 2 are marked as fault periods, and the fault distribution data is 2 / 3.

[0081] Next, at least two of the number of fault types marked as non-easy-to-manage faults, the mean relative frequency of faults, and the fault distribution data can be weighted averaged to obtain a fault summary value. For example, the mean relative frequency of faults and the fault distribution data can be weighted averaged to obtain a fault summary. For another example, the number of fault types marked as non-easy-to-manage faults, the mean relative frequency of faults, and the fault distribution data can be weighted averaged to obtain a fault summary value, that is, the fault summary value can be determined according to the following formula:

[0082] GX=(hy1*GY+hy2*GK+hy3*GN) / 3

[0083] Among them, GX is the fault summary value; GY is the number of fault types marked as non-manageable faults;

[0084] GK is the mean relative frequency of faults; GN is the fault distribution data; hy1, hy2, and hy3 are preset proportional coefficients, all of which are positive numbers and can be set according to actual needs, which is not limited in the present disclosure.

[0085] Finally, a fault risk signal can be generated based on the fault summary value and the preset summary threshold. Specifically, if the fault summary value GX is greater than the preset summary threshold, it indicates that the operating performance of the instrument equipment in the preset period is poor and the fault risk is high, and a high fault risk signal is generated; if the fault summary value GX is less than or equal to the preset summary threshold, it indicates that the operating performance of the instrument equipment in the preset period is good and the fault risk is low, and a low fault risk signal is generated.

[0086] This embodiment comprehensively considers multiple factors: the number of fault types that can intuitively reflect the richness of existing fault types, the mean value of the relative frequency of faults that reflects the relative frequency of occurrence of various faults, and the fault distribution data that reflects the distribution characteristics of faults in time and space, so that the fault situation can be comprehensively measured from different angles to obtain a more accurate fault risk signal.

[0087] For step S105, when it is implemented, the occurrence time and elimination time of the fault can be obtained from the operation log of the instrument equipment. The repair evaluation indicators include: a repair abnormality ratio indicator used to reflect the relative degree of abnormal repair conditions in the overall operation and maintenance repair work, and a repair time ratio indicator used to reflect the average deviation between the overall repair time and the preset standard time.

[0088] In one possible implementation, the repair time of each fault can be determined based on the occurrence time of each fault and the corresponding elimination time; then, each repair time is marked as abnormal based on the repair time and the corresponding preset repair time; finally, the repair abnormality ratio index value is determined based on the number of repair times with abnormal marks and the total number of repair times; if the repair abnormality ratio index value is greater than the preset repair abnormality ratio, a fault repair unqualified signal is generated; if the repair abnormality ratio index value is less than or equal to the preset repair abnormality ratio, a fault repair qualified signal is generated.

[0089] In another possible implementation, the calculating of the index value of at least one repair evaluation index according to the acquired occurrence time and elimination time of each fault, and generating the fault repair status signal according to the index value of the at least one repair evaluation index, includes:

[0090] Step S1051: determining each repair time according to each occurrence time and the corresponding elimination time; marking each repair time as abnormal according to each repair time and the corresponding preset repair time; determining a repair abnormality ratio index value according to the number of repair times with abnormal marks and the total number of repair times;

[0091] Step S1052: for any target repair time, determine a repair time ratio value according to the target repair time and the corresponding preset repair time; and determine a repair time ratio index value according to the repair time ratio values ​​of all faults;

[0092] Step S1053: determining a repair evaluation value according to the repair abnormality proportion index value and the preset first proportional coefficient, the repair time proportion index value and the preset second proportional coefficient;

[0093] Step S1054: Generate a fault repair status signal according to the repair evaluation value and a preset repair evaluation threshold.

[0094] During implementation, for any fault, the time difference between the elimination time and the occurrence time of the fault can be calculated to obtain the repair time of the fault. Then, according to each repair time and the corresponding preset repair time, each repair time is marked as abnormal. Among them, the preset repair time can be set according to the type of fault. This is not limited in the present disclosure. Specifically, if the repair time is longer than the corresponding preset repair time, it indicates that the operation and maintenance repair process for the fault is relatively slow, and the corresponding repair time is marked as abnormal. Finally, the ratio of the number of repair times with abnormal marks to the total number of repair times is calculated to obtain the repair abnormality ratio index value. Then, for any target repair time, the ratio of the target repair time to the corresponding preset repair time can be calculated to obtain the repair time share value; the average of each repair time share value is taken to obtain the repair time share index value.

[0095] Then, the product of the repair abnormality ratio index value and the preset first proportional coefficient can be added to the product of the repair time ratio index value and the preset second proportional coefficient to obtain the repair evaluation value. That is, the repair evaluation value can be determined according to the following formula:

[0096] LP=ew1*LK+ew2*LS

[0097] Among them, LP is the repair evaluation value; ew1 is the preset first proportional coefficient; LK is the repair abnormality ratio index value; ew2 is the preset second proportional coefficient; LS is the repair time ratio index value. Here, ew1 and ew2 can be set according to actual needs, and are not limited by this disclosure. For example, if the repair abnormality ratio index value is considered to be more important in the overall evaluation, ew1>ew2>0 can be set.

[0098] After obtaining the repair evaluation value, a fault repair status signal can be generated by comparing the repair evaluation value and the preset repair evaluation threshold. It can be understood that the larger the value of the repair evaluation value LP is, the worse the operation and maintenance repair situation of the fault in the fault diagnosis result is. Therefore, if the repair evaluation value LP is greater than the preset repair evaluation threshold, a fault repair failure signal is generated; if the repair evaluation value LP is less than or equal to the preset repair evaluation threshold, a fault repair qualification signal is generated.

[0099] The solution provided in this embodiment comprehensively considers two factors: maintenance efficiency and the average level of overall repair time utilization, so that the fault repair situation can be accurately evaluated.

[0100] For step S106, if a fault repair failure signal is generated, the subsequent instrument equipment operation supervision and fault operation and maintenance management can be strengthened to ensure the safe and stable operation of the corresponding instrument equipment and reduce the operation risks of the corresponding instrument equipment; if the fault repair status signal is a fault repair qualified signal, the index value of at least one operation and maintenance evaluation index can be calculated based on the operation and maintenance monitoring data of each fault, and an operation and maintenance evaluation signal can be generated based on the index value of the at least one operation and maintenance evaluation index. Here, the operation and maintenance monitoring data includes, for example, the alarm time when the target personnel who repairs a certain fault receives the alarm signal, the operation and maintenance time when the target personnel starts operation and maintenance, the processing time of the operation and maintenance process, the number of mistakes made by the target personnel during the operation and maintenance process, etc. The operation and maintenance evaluation indicators include, for example, the number of abnormal operation and maintenance processes, the abnormal operation and maintenance ratio index, etc.

[0101] In a possible implementation, the operation and maintenance monitoring data includes: the alarm time when the target personnel receives the alarm signal, the operation and maintenance time when the target personnel starts the operation and maintenance, and the processing time of the operation and maintenance process. The preparation time corresponding to each fault can be determined according to the alarm time when the target personnel receives the alarm signal and the operation and maintenance time when the target personnel starts the operation and maintenance; for any fault, if at least one of the following is met, the abnormal operation and maintenance process is marked: the preparation time is greater than the corresponding preset preparation time, the preparation time is less than or equal to the corresponding preset preparation time, and the processing time is greater than the preset processing time threshold; if the number of abnormal operation and maintenance processes is greater than the preset number of abnormal operation and maintenance processes, an operation and maintenance poor evaluation signal is generated; if the number of abnormal operation and maintenance processes is less than or equal to the preset number of abnormal operation and maintenance processes, an operation and maintenance good evaluation signal is generated.

[0102] In a possible implementation manner, the operation and maintenance monitoring data includes: the alarm time when the target personnel receives the alarm signal, the operation and maintenance time when the target personnel starts to perform operation and maintenance, the processing time of the operation and maintenance process, and the number of mistakes made by the target personnel during the operation and maintenance process; the operation and maintenance monitoring data of each fault is obtained, the index value of at least one operation and maintenance evaluation index is calculated, and the operation and maintenance evaluation signal is generated according to the index value of the at least one operation and maintenance evaluation index, including:

[0103] Step S1061: determining the preparation time corresponding to each fault according to the alarm time when the target personnel receives the alarm signal and the operation and maintenance time when the target personnel starts the operation and maintenance;

[0104] Step S1062: For any fault, if at least one of the following is met, an abnormal operation and maintenance process is marked: the preparation time is greater than the corresponding preset preparation time, the preparation time is less than or equal to the corresponding preset preparation time and the processing time is greater than the preset processing time threshold, the preparation time is less than or equal to the corresponding preset preparation time and the number of errors is greater than the preset number of errors threshold;

[0105] Step S1064: Determine the abnormal operation and maintenance ratio index value according to the number of abnormal operation and maintenance processes and the total number of operation and maintenance processes;

[0106] Step S1065: If at least one of the following is met, a poor operation and maintenance rating signal is generated; otherwise, a good operation and maintenance rating signal is generated: the number of abnormal operation and maintenance processes is greater than the preset number of abnormal operation and maintenance processes, and the abnormal operation and maintenance ratio index value is greater than the preset abnormal operation and maintenance ratio threshold.

[0107] During implementation, the time difference between the alarm time and the corresponding operation and maintenance time can be calculated to obtain the preparation time corresponding to each fault. Among them, the larger the value of the preparation time, the lower the preparation efficiency of the corresponding operation and maintenance process. For any fault, if the preparation time is greater than the corresponding preset preparation time, the operation and maintenance process of the fault is marked as an abnormal operation and maintenance process; if the preparation time is less than or equal to the preset preparation time, the processing time of the operation and maintenance process of the fault and the number of errors made by the target personnel in the operation and maintenance process can be obtained; if the processing time is greater than the preset processing time threshold, the operation and maintenance process of the fault is marked as an abnormal operation and maintenance process; if the number of errors is greater than the preset error number threshold, the operation and maintenance process of the fault is marked as an abnormal operation and maintenance process. Among them, the preset preparation time, the preset processing time threshold, and the preset error number threshold can be set according to actual needs, and this is not limited to the embodiments of the present disclosure.

[0108] After marking the operation and maintenance process of each fault as abnormal, the ratio of the number of abnormal operation and maintenance processes to the total number of operation and maintenance processes can be calculated to obtain the abnormal operation and maintenance ratio index value. Then, the number of abnormal operation and maintenance processes can be compared with the preset number of abnormal operation and maintenance processes, and the abnormal operation and maintenance ratio index value can be compared with the preset abnormal operation and maintenance ratio threshold value; if the number of abnormal operation and maintenance processes is greater than the preset number of abnormal operation and maintenance processes, and the abnormal operation and maintenance ratio index value is greater than the preset abnormal operation and maintenance ratio threshold value, then a poor operation and maintenance evaluation signal is generated; if the number of abnormal operation and maintenance processes is greater than the preset number of abnormal operation and maintenance processes, and the abnormal operation and maintenance ratio index value is less than or equal to the preset abnormal operation and maintenance ratio threshold value, then a poor operation and maintenance evaluation signal is generated; if the number of abnormal operation and maintenance processes is less than or equal to the preset number of abnormal operation and maintenance processes, and the abnormal operation and maintenance ratio index value is greater than the preset abnormal operation and maintenance ratio threshold value, then a poor operation and maintenance evaluation signal is generated; if the number of abnormal operation and maintenance processes is less than or equal to the preset number of abnormal operation and maintenance processes, and the abnormal operation and maintenance ratio index value is less than or equal to the preset abnormal operation and maintenance ratio threshold value, then a good operation and maintenance evaluation signal is generated.

[0109] This embodiment can evaluate the operation and maintenance situation from the perspective of absolute quantity, and from the perspective of relative proportion, and complement each other, so as to obtain a more accurate, comprehensive and scientific operation and maintenance evaluation signal, based on which the subsequent operation and maintenance personnel training and operation and maintenance personnel supervision can be strengthened to ensure the subsequent operation and maintenance efficiency and operation and maintenance effect of the instrument equipment.

[0110] The present disclosure also provides a method for diagnosing a fault in an instrument device, comprising the following steps:

[0111] Step S1: Acquire the equipment operation data of multiple instrument equipment in the target site in real time.

[0112] Step S2: Using the trained fault risk judgment model, the equipment operation data of multiple instrument equipment and the actual working condition data of the target site are processed to obtain the fault risk existence result corresponding to each instrument equipment.

[0113] In specific implementation, the trained fault risk judgment model is generated according to the following method: obtaining a training set; wherein the characteristic data of the samples in the training set include sample equipment operation data and sample operating condition data of multiple instrument equipment in the target site, and the sample label is the presence of fault risk / no fault risk; inputting the characteristic data of each sample in the training set into the fault risk judgment model to be trained to obtain each fault risk prediction value; calculating each loss value according to each fault risk prediction value, the corresponding sample label, and a preset loss function; using each loss value, updating the parameters in the fault risk judgment model to be trained to obtain a trained fault risk judgment model.

[0114] Step S3: For any target instrument equipment with a fault risk, a target fault diagnosis result is generated based on the trained fault diagnosis model, the equipment operation data and fault-related data of the target instrument equipment; wherein the fault-related data includes at least one of the following: operation logs and maintenance records; the target fault diagnosis result includes the fault type, fault location and fault cause.

[0115] In specific implementation, the trained fault diagnosis model can be used to process the equipment operation data and fault-related data of the target instrument equipment to obtain the fault mode recognition result; based on the preset first mapping relationship, the acquired real-time operation data of the target instrument equipment and the fault mode recognition result are used to generate the fault type and fault location; wherein the preset first mapping relationship represents the correspondence between the real-time operation data and fault mode of the instrument equipment and the fault type and fault location; based on the preset second mapping relationship,

[0116] According to the fault type, the fault cause is determined; wherein the preset second mapping relationship represents the corresponding relationship between the fault type and the fault cause.

[0117] Step S4: For any target operation and maintenance personnel, determine the target operation and maintenance selection data based on at least two of the following items: target operation and maintenance distance, target operation and maintenance times, and target abnormal operation and maintenance times; wherein the target operation and maintenance distance is determined based on the location data of the target faulty instrument equipment and the location data of the target operation and maintenance personnel; the target operation and maintenance times is the total number of times the target operation and maintenance personnel perform operation and maintenance on the target fault type corresponding to the target faulty instrument equipment; the target abnormal operation and maintenance times is the number of abnormal operation and maintenance processes performed by the target operation and maintenance personnel within a preset detection period.

[0118] Step S5: Determine at least one target person according to each target operation and maintenance selection data.

[0119] Step S6: Send an alarm signal to a terminal used by at least one target person.

[0120] Step S7: Calculate the index value of at least one fault evaluation index based on the acquired fault occurrence status data of multiple instrument devices within a preset period, and generate a fault risk signal based on the index value of at least one fault evaluation index.

[0121] In specific implementation, if the fault occurrence status data includes: the fault types of all faults occurring in multiple instrument devices, the number of occurrences of each fault type, and the occurrence time of each fault; then, based on the acquired fault occurrence status data of multiple instrument devices within a preset period, the index value of at least one fault evaluation index is calculated, and based on the index value of at least one fault evaluation index, a fault risk signal is generated, including: marking each fault type as a non-easy-to-manage fault according to the number of occurrences of each fault type and the corresponding preset number of fault occurrences; if the number of fault types marked as non-easy-to-manage faults is greater than the preset number of non-easy-to-manage faults, a high-risk fault signal is generated .... If the number of fault types of faults is less than or equal to the preset number of non-easy-to-manage, the mean relative frequency of faults is determined according to the number of occurrences and the corresponding preset number of fault occurrences; the total number of fault occurrences in each target time period is determined according to the occurrence time of each fault, and each target time period is marked as a fault time period according to the preset total number of fault occurrences; the fault distribution data is determined according to the number of target time periods marked as fault time periods and the total number of target time periods; a weighted average is performed on at least two of the number of fault types marked as non-easy-to-manage faults, the mean relative frequency of faults, and the fault distribution data to obtain a fault summary value; a fault risk signal is generated according to the fault summary value and the preset summary threshold.

[0122] Step S8: Calculate the index value of at least one repair evaluation index according to the acquired occurrence time and elimination time of each fault, and generate a fault repair status signal according to the index value of at least one repair evaluation index.

[0123] In specific implementation, each repair time can be determined according to each occurrence time and the corresponding elimination time; each repair time can be marked as abnormal according to the each repair time and the corresponding preset repair time; the repair abnormality proportion index value can be determined according to the number of repair times with abnormal markings and the total number of repair times; for any target repair time, the repair time proportion value can be determined according to the target repair time and the corresponding preset repair time; and the repair time proportion index value can be determined according to the repair time proportion values ​​of all faults; the repair evaluation value can be determined according to the repair abnormality proportion index value and the preset first proportional coefficient, the repair time proportion index value and the preset second proportional coefficient; and the fault repair status signal can be generated according to the repair evaluation value and the preset repair evaluation threshold.

[0124] Step S9: If the fault repair status signal is a fault repair qualified signal, calculate the index value of at least one operation and maintenance evaluation index according to the acquired operation and maintenance monitoring data of each fault, and generate an operation and maintenance evaluation signal according to the index value of at least one operation and maintenance evaluation index.

[0125] In specific implementation, if the operation and maintenance monitoring data includes: the alarm time when the target personnel receives the alarm signal, the operation and maintenance time when the target personnel starts to perform operation and maintenance, the processing time of the operation and maintenance process, and the number of mistakes made by the target personnel during the operation and maintenance process; then according to the operation and maintenance monitoring data of each fault obtained, the index value of at least one operation and maintenance evaluation index is calculated, and according to the index value of at least one operation and maintenance evaluation index, an operation and maintenance evaluation signal is generated, including: according to the alarm time when the target personnel receives the alarm signal and the operation and maintenance time when the target personnel starts to perform operation and maintenance, the preparation time corresponding to each fault is determined; for any fault, if at least one of the following is satisfied , then the abnormal operation and maintenance process is marked: the preparation time is greater than the corresponding preset preparation time, the preparation time is less than or equal to the corresponding preset preparation time and the processing time is greater than the preset processing time threshold, the preparation time is less than or equal to the corresponding preset preparation time and the number of errors is greater than the preset number of errors threshold; according to the number of abnormal operation and maintenance processes and the total number of operation and maintenance processes, the abnormal operation and maintenance proportion index value is determined; if at least one of the following is met, an operation and maintenance poor evaluation signal is generated, otherwise, an operation and maintenance good evaluation signal is generated: the number of abnormal operation and maintenance processes is greater than the preset number of abnormal operation and maintenance processes, and the abnormal operation and maintenance proportion index value is greater than the preset abnormal operation and maintenance proportion threshold.

[0126] Those skilled in the art will appreciate that, in the above method of the specific implementation manner, the writing order of the steps does not mean a strict execution order, but does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0127] It should be noted that, in practical applications, all possible implementations described above can be combined in any manner to form possible embodiments of the present disclosure, which will not be described one by one here.

[0128] Based on the same concept, the embodiment of the present disclosure also provides a device for diagnosing instrument faults. Figure 2 The schematic diagram of the structure of the instrument equipment fault diagnosis device provided by the embodiment of the present disclosure is shown in FIG. Figure 2 As shown, the instrument equipment fault diagnosis device 200 provided in the embodiment of the present disclosure includes:

[0129] Acquisition module 201, used to acquire equipment operation data of multiple instrument equipment in the target site in real time;

[0130] The risk existence judgment module 202 is used to process the equipment operation data of the plurality of instrument equipment and the actual working condition data of the target site by using the trained fault risk judgment model to obtain the fault risk existence result corresponding to each instrument equipment;

[0131] The fault diagnosis module 203 is used to generate a target fault diagnosis result for any target instrument equipment with a fault risk based on a trained fault diagnosis model, the equipment operation data and fault-related data of the target instrument equipment; wherein the fault-related data includes at least one of the following: an operation log and a maintenance record; and the target fault diagnosis result includes the fault type, fault location and fault cause.

[0132] In one possible implementation, the device further includes a judgment model training module, which is used to: obtain a training set; wherein the characteristic data of the samples in the training set include sample equipment operation data and sample operating condition data of multiple instrument equipment in the target site, and the sample label is whether there is a fault risk / there is no fault risk; input the characteristic data of each sample in the training set into the fault risk judgment model to be trained to obtain each fault risk prediction value; calculate each loss value based on each fault risk prediction value, the corresponding sample label, and a preset loss function; and use the each loss value to update the parameters in the fault risk judgment model to be trained to obtain the trained fault risk judgment model.

[0133] In a possible implementation, in the above-mentioned device, the fault diagnosis module 203 is used to: use the trained fault diagnosis model to process the equipment operation data and fault-related data of the target instrument equipment to obtain a fault mode recognition result; based on a preset first mapping relationship, use the acquired real-time operation data of the target instrument equipment and the fault mode recognition result to generate a fault type and a fault location; wherein the preset first mapping relationship represents the correspondence between the real-time operation data and fault mode of the instrument equipment and the fault type and fault location; based on a preset second mapping relationship, determine the cause of the fault according to the fault type; wherein the preset second mapping relationship represents the correspondence between the fault type and the fault cause.

[0134] Figure 3 FIG. 1 is a schematic diagram showing a structure of an instrument equipment fault diagnosis device provided by another embodiment of the present disclosure; Figure 3 As shown, the instrument equipment fault diagnosis device 200 provided in the embodiment of the present disclosure also includes:

[0135] The alarm module 204 is used to determine the target operation and maintenance selection data for any target operation and maintenance personnel based on at least two of the following items: target operation and maintenance distance, target operation and maintenance times, and target abnormal operation and maintenance times; wherein the target operation and maintenance distance is determined based on the location data of the target fault instrument equipment and the location data of the target operation and maintenance personnel; the target operation and maintenance times are the total number of times the target operation and maintenance personnel perform operation and maintenance on the target fault type corresponding to the target fault instrument equipment; the target abnormal operation and maintenance times are the number of abnormal operation and maintenance processes performed by the target operation and maintenance personnel within a preset detection period; at least one target personnel is determined based on each of the target operation and maintenance selection data; and an alarm signal is sent to a terminal used by the at least one target personnel.

[0136] In a possible implementation manner, the device further includes:

[0137] The fault evaluation module 205 is used to calculate the index value of at least one fault evaluation index according to the acquired fault occurrence status data of the plurality of instrument devices within a preset period, and generate a fault risk signal according to the index value of the at least one fault evaluation index;

[0138] A repair evaluation module 206, configured to calculate an index value of at least one repair evaluation index according to the acquired occurrence time and elimination time of each fault, and generate a fault repair state signal according to the index value of the at least one repair evaluation index;

[0139] The operation and maintenance evaluation module 207 is used to calculate the index value of at least one operation and maintenance evaluation index according to the acquired operation and maintenance monitoring data of each fault if the fault repair status signal is a fault repair qualified signal, and generate an operation and maintenance evaluation signal according to the index value of the at least one operation and maintenance evaluation index.

[0140] In a possible implementation manner, in the above-mentioned device, the fault occurrence status data includes: the fault types of all faults occurring in the plurality of instrument devices, the number of occurrences of each fault type, and the occurrence time of each fault; the fault evaluation module 205 is used to: mark each of the fault types as non-easy-to-manage faults according to the number of occurrences of each fault type and the corresponding preset number of occurrences of the fault; if the number of fault types marked as non-easy-to-manage faults is greater than the preset number of non-easy-to-manage faults, generate a high-risk fault signal; if the number of fault types marked as non-easy-to-manage faults is less than or equal to the preset number of non-easy-to-manage faults, generate a high-risk fault signal according to each fault type; The number of occurrences and the corresponding preset number of fault occurrences are used to determine the mean relative frequency of faults; the total number of fault occurrences in each target time period is determined according to the occurrence time of each fault, and each target time period is marked as a fault time period according to the preset total number of fault occurrences; the fault distribution data is determined according to the number of target time periods marked as fault time periods and the total number of target time periods; a weighted average is performed on the number of fault types marked as non-easy-to-manage faults, the mean relative frequency of faults, and at least two of the fault distribution data to obtain a fault summary value; a fault risk signal is generated according to the fault summary value and a preset summary threshold.

[0141] In a possible implementation, in the above-mentioned device, the repair evaluation module 206 is used to: determine each repair time according to each occurrence time and the corresponding elimination time; mark each repair time as abnormal according to each repair time and the corresponding preset repair time; determine the repair abnormality proportion index value according to the number of repair times with abnormal markings and the total number of repair times; for any target repair time, determine the repair time proportion value according to the target repair time and the corresponding preset repair time; and determine the repair time proportion index value according to the repair time proportion values ​​of all faults; determine the repair evaluation value according to the repair abnormality proportion index value and the preset first proportional coefficient, the repair time proportion index value and the preset second proportional coefficient; generate a fault repair status signal according to the repair evaluation value and the preset repair evaluation threshold.

[0142] In a possible implementation manner, in the above-mentioned device, the operation and maintenance monitoring data includes: the alarm time when the target personnel receives the alarm signal, the operation and maintenance time when the target personnel starts to perform operation and maintenance, the processing time of the operation and maintenance process, and the number of errors made by the target personnel during the operation and maintenance process; the operation and maintenance evaluation module 207 is used to: determine the preparation time corresponding to each fault according to the alarm time when the target personnel receives the alarm signal and the operation and maintenance time when the target personnel starts to perform operation and maintenance; for any fault, if at least one of the following is met, an abnormal operation and maintenance process is marked: the preparation time is greater than the corresponding preset preparation time, the preparation time is less than or equal to the corresponding preset preparation time and the processing time is greater than the preset processing time threshold, the preparation time is less than or equal to the corresponding preset preparation time and the number of errors is greater than the preset number of errors threshold; determine the abnormal operation and maintenance ratio index value according to the number of abnormal operation and maintenance processes and the total number of operation and maintenance processes; if at least one of the following is met, generate an operation and maintenance poor evaluation signal, otherwise, generate an operation and maintenance good evaluation signal: the number of abnormal operation and maintenance processes is greater than the preset number of abnormal operation and maintenance processes, and the abnormal operation and maintenance ratio index value is greater than the preset abnormal operation and maintenance ratio threshold.

[0143] It should be noted that any of the above-mentioned instrument equipment fault diagnosis devices can implement the above-mentioned instrument equipment fault diagnosis method one by one, which will not be repeated here.

[0144] Figure 4 FIG. 1 shows a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Figure 4 As shown, at the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Among them, the memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage, etc. Of course, the electronic device may also include hardware required for other services.

[0145] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0146] The memory is used to store programs. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory may include internal memory and non-volatile memory, and provides instructions and data to the processor.

[0147] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming an instrument equipment fault diagnosis device at the logical level. The processor executes the program stored in the memory and is specifically used to execute the above method.

[0148] The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present disclosure may be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present disclosure may be directly embodied as being executed by a hardware decoding processor, or may be executed by a combination of hardware and software modules in a decoding processor. The software module may be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0149] The electronic device can execute the instrument equipment fault diagnosis method provided by multiple embodiments of the present disclosure, and realize the instrument equipment fault diagnosis device in Figure 2 The functions of the embodiments shown in or 3 are not described in detail in the embodiments of the present disclosure.

[0150] The embodiments of the present disclosure also propose a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, can enable the electronic device to execute the instrument equipment fault diagnosis method provided by multiple embodiments of the present disclosure.

[0151] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0152] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0153] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0154] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0155] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0156] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0157] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0158] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity or device including the element.

[0159] It will be appreciated by those skilled in the art that the embodiments of the present disclosure may be provided as methods, systems or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0160] The above are only embodiments of the present disclosure and are not intended to limit the present disclosure. For those skilled in the art, the present disclosure may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present disclosure shall be included in the scope of the claims of the present disclosure.

Claims

1. A method for diagnosing instrument equipment faults, characterized in that: The method comprises: Obtain equipment operation data of multiple instruments and equipment in the target site in real time; Using the trained fault risk judgment model, the equipment operation data of the multiple instrument equipment and the actual working condition data of the target site are processed to obtain the fault risk existence result corresponding to each instrument equipment; For any target instrument equipment with a risk of failure, a target fault diagnosis result is generated based on a trained fault diagnosis model, the equipment operation data and fault-related data of the target instrument equipment; wherein the fault-related data includes at least one of the following: an operation log and a maintenance record; the target fault diagnosis result includes the fault type, fault location and fault cause; For any target instrument equipment with a risk of failure, generating a target fault diagnosis result based on the trained fault diagnosis model, the equipment operation data and the fault-related data of the target instrument equipment, includes: Using the trained fault diagnosis model, the equipment operation data and fault-related data of the target instrument equipment are processed to obtain a fault mode recognition result; Based on a preset first mapping relationship, the real-time operation data of the target instrument equipment and the fault mode recognition result obtained are used to generate a fault type and a fault location; wherein the preset first mapping relationship represents the correspondence between the real-time operation data of the instrument equipment, the fault mode, and the fault type and the fault location; Based on a preset second mapping relationship, the cause of the fault is determined according to the fault type; wherein the preset second mapping relationship represents a corresponding relationship between the fault type and the fault cause.

2. The method according to claim 1, characterized in that The trained fault risk judgment model is generated according to the following method: Acquire a training set; wherein the characteristic data of the samples in the training set include sample equipment operation data and sample working condition data of multiple instrument equipment in the target site, and the labels of the samples are existence of failure risk / no failure risk; Inputting the characteristic data of each sample in the training set into the fault risk judgment model to be trained to obtain each fault risk prediction value; Calculate each loss value according to each of the fault risk prediction values, the corresponding sample labels, and a preset loss function; The parameters in the fault risk judgment model to be trained are updated by using the loss values ​​to obtain the trained fault risk judgment model.

3. The method according to claim 1, characterized in that The method further comprises: For any target operation and maintenance personnel, the target operation and maintenance selection data is determined according to at least two of the following items: target operation and maintenance distance, target operation and maintenance times, and target abnormal operation and maintenance times; wherein the target operation and maintenance distance is determined according to the location data of the target fault instrument equipment and the location data of the target operation and maintenance personnel; the target operation and maintenance times is the total number of times the target operation and maintenance personnel perform operation and maintenance on the target fault type corresponding to the target fault instrument equipment; the target abnormal operation and maintenance times is the number of abnormal operation and maintenance processes performed by the target operation and maintenance personnel within a preset detection period; Determining at least one target person according to each of the target operation and maintenance selection data; An alarm signal is sent to a terminal used by the at least one target person.

4. The method according to claim 3, characterized in that The method further comprises: Calculate the index value of at least one fault evaluation index according to the acquired fault occurrence status data of the plurality of instrument devices within a preset period, and generate a fault risk signal according to the index value of the at least one fault evaluation index; Calculate at least one repair evaluation index value according to the acquired occurrence time and elimination time of each fault, and generate a fault repair state signal according to the index value of the at least one repair evaluation index; If the fault repair status signal is a fault repair qualified signal, the index value of at least one operation and maintenance evaluation index is calculated according to the acquired operation and maintenance monitoring data of each fault, and an operation and maintenance evaluation signal is generated according to the index value of the at least one operation and maintenance evaluation index.

5. The method according to claim 4, characterized in that The fault occurrence status data includes: the fault types of all faults occurring in the multiple instrument devices, the number of occurrences of each fault type, and the occurrence time of each fault; the calculation of the index value of at least one fault evaluation index based on the acquired fault occurrence status data of the multiple instrument devices within a preset period, and the generation of a fault risk signal based on the index value of the at least one fault evaluation index, including: According to the number of occurrences of each fault type and the corresponding preset number of occurrences of each fault type, marking each fault type as a non-manageable fault; If the number of fault types marked as non-easy-to-manage faults is greater than a preset number of non-easy-to-manage faults, a high-risk fault signal is generated; If the number of fault types marked as non-easy-to-manage faults is less than or equal to the preset number of non-easy-to-manage faults, determining a mean value of the relative frequency of the faults according to the number of occurrences and the corresponding preset number of occurrences of the faults; According to the occurrence time of each fault, determine the total number of faults in each target time period, and mark each target time period as a fault time period according to the preset total number of faults; determine fault distribution data according to the number of target time periods marked as fault time periods and the total number of target time periods; Performing weighted averaging on at least two of the number of fault types marked as non-easy-to-manage faults, the mean value of the relative frequency of the faults, and the fault distribution data to obtain a fault summary value; A fault risk signal is generated according to the fault summary value and a preset summary threshold.

6. The method according to claim 4, characterized in that The step of calculating the index value of at least one repair evaluation index according to the acquired occurrence time and elimination time of each fault, and generating a fault repair state signal according to the index value of the at least one repair evaluation index comprises: Determine each repair time according to each occurrence time and the corresponding elimination time; mark each repair time as abnormal according to each repair time and the corresponding preset repair time; determine the repair abnormality proportion index value according to the number of repair times with abnormal marks and the total number of repair times; For any target repair time, determine the repair time value according to the target repair time and the corresponding preset repair time; and determine the repair time proportion index value according to the repair time values ​​of all faults; Determine a repair evaluation value according to the repair anomaly proportion index value and a preset first proportional coefficient, the repair time proportion index value and a preset second proportional coefficient; A fault repair state signal is generated according to the repair evaluation value and a preset repair evaluation threshold.

7. The method according to any one of claims 4 to 6, characterized in that: The operation and maintenance monitoring data includes: the alarm time when the target personnel receives the alarm signal, the operation and maintenance time when the target personnel starts the operation and maintenance, the processing time of the operation and maintenance process, and the number of mistakes made by the target personnel during the operation and maintenance process; the operation and maintenance monitoring data of each fault acquired are used to calculate the index value of at least one operation and maintenance evaluation index, and the operation and maintenance evaluation signal is generated according to the index value of the at least one operation and maintenance evaluation index, including: Determine the preparation time corresponding to each fault according to the alarm time when the target personnel receives the alarm signal and the operation and maintenance time when the target personnel starts the operation and maintenance; For any fault, if at least one of the following is met, an abnormal operation and maintenance process mark is performed: the preparation time is greater than the corresponding preset preparation time, the preparation time is less than or equal to the corresponding preset preparation time and the processing time is greater than the preset processing time threshold, the preparation time is less than or equal to the corresponding preset preparation time and the number of errors is greater than the preset number of errors threshold; Determine the abnormal operation and maintenance ratio indicator value based on the number of abnormal operation and maintenance processes and the total number of operation and maintenance processes; If at least one of the following is met, a poor operation and maintenance rating signal is generated; otherwise, a good operation and maintenance rating signal is generated: the number of abnormal operation and maintenance processes is greater than the preset number of abnormal operation and maintenance processes, and the abnormal operation and maintenance ratio index value is greater than the preset abnormal operation and maintenance ratio threshold.

8. An instrument equipment fault diagnosis device, characterized in that: The device comprises: An acquisition module is used to acquire the equipment operation data of multiple instrument equipment in the target site in real time; A risk existence judgment module is used to process the equipment operation data of the plurality of instrument equipment and the actual working condition data of the target site by using the trained fault risk judgment model to obtain the fault risk existence result corresponding to each instrument equipment; A fault diagnosis module is used to generate a target fault diagnosis result for any target instrument equipment with a fault risk based on a trained fault diagnosis model, equipment operation data of the target instrument equipment and fault-related data; wherein the fault-related data includes at least one of the following: an operation log and a maintenance record; and the target fault diagnosis result includes a fault type, a fault location and a fault cause; The fault diagnosis module is used to use the trained fault diagnosis model to process the equipment operation data and fault-related data of the target instrument equipment to obtain a fault mode recognition result; based on a preset first mapping relationship, use the acquired real-time operation data of the target instrument equipment and the fault mode recognition result to generate a fault type and a fault location; wherein the preset first mapping relationship represents the correspondence between the real-time operation data and fault mode of the instrument equipment and the fault type and fault location; based on a preset second mapping relationship, determine the cause of the fault according to the fault type; wherein the preset second mapping relationship represents the correspondence between the fault type and the fault cause.

9. An electronic device, comprising: processor; as well as A memory arranged to store computer executable instructions, wherein the executable instructions, when executed, cause the processor to perform the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing one or more programs, characterized in that: When the one or more programs are executed by an electronic device including a plurality of application programs, the electronic device executes the steps of the method as claimed in any one of claims 1 to 7.

Images