Fault diagnosis system and method for electrical equipment of coal preparation plant

Abstract

The invention discloses a coal preparation plant electrical equipment fault diagnosis system and method, relates to the technical field of electrical equipment fault diagnosis, and solves the problems that in the prior art, dynamic interference of dust deposition on a heat conduction path is neglected, dust deposits on the surface of equipment to form a heat insulation layer, heat dissipation of the equipment is affected, the heat dissipation efficiency of the equipment is reduced, and the service life of the equipment is prolonged. And the deviation between the predicted equipment temperature and the actual temperature in the prior art is large. The method comprises the steps of obtaining operation data and environment data of electrical equipment of a coal preparation plant; predicting the operation data of the equipment based on a pre-trained temperature prediction model to obtain predicted operation data; calculating a target dust deposition rate based on the environmental data; correcting the predicted operation data based on the target dust deposition rate to obtain target operation data; calculating a fault evaluation coefficient of the equipment based on the target operation data; and judging whether early warning is performed based on the fault evaluation coefficient of the equipment. The technical problem is solved.

Description

Technical Field

[0001] The invention belongs to the field of electrical equipment fault diagnosis, and in particular relates to a coal preparation plant electrical equipment fault diagnosis system and method. Background Art

[0002] Coal preparation plants, as the core link in coal washing and processing, are subject to complex operating conditions characterized by high loads, high dust levels, and high vibration. These plants are prone to problems such as emergency stop protection failures, deviation protection failures, malfunctioning pull-cord switches, damaged electrical components (such as contactor burnout and circuit breaker failures), and abnormal motor protection. Traditional fault diagnosis methods, which rely heavily on manual experience, suffer from delayed response, high rates of missed detection, and low diagnostic efficiency. These methods struggle to meet the stringent requirements of coal preparation plants for equipment stability and safe production.

[0003] In existing technologies, fault diagnosis for electrical equipment mostly relies on threshold judgments of sensor data or simple predictions based on static models. For example, artificial intelligence is used to perform predictions and early warnings by monitoring physical parameters such as equipment temperature, voltage, and current. However, existing technologies ignore the dynamic interference of dust deposition on the heat conduction path. Dust deposition on the surface of the equipment will form an insulating layer, significantly reducing the heat dissipation efficiency. As time goes by, the dust deposition will increase, thereby affecting the heat dissipation of the equipment, resulting in a large deviation between the equipment temperature predicted by existing technologies and the actual temperature.

[0004] Therefore, the present invention solves the above problems by proposing a coal preparation plant electrical equipment fault diagnosis system and method. Summary of the Invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a coal preparation plant electrical equipment fault diagnosis system and method, which is used to solve the technical problem that the prior art ignores the dynamic interference of dust deposition on the heat conduction path. Dust deposition on the surface of the equipment will form an insulating layer, which significantly reduces the heat dissipation efficiency. As time goes by, the dust deposition will increase, thereby affecting the heat dissipation of the equipment, resulting in a large deviation between the equipment temperature predicted by the prior art and the actual temperature.

[0006] To achieve the above-mentioned object, a first aspect of the present invention provides a coal preparation plant electrical equipment fault diagnosis system, comprising: a data acquisition module, a data analysis module and a fault diagnosis module;

[0007] Data acquisition module: used to obtain operating data and environmental data of electrical equipment in coal preparation plants;

[0008] Data analysis module: Predict the operating data of the device based on a pre-trained temperature prediction model to obtain predicted operating data; calculate the target dust deposition rate based on environmental data; correct the predicted operating data based on the target dust deposition rate to obtain target operating data; and,

[0009] Calculate the fault assessment coefficient of the device based on the target operating data;

[0010] Fault diagnosis module: Determine whether to give an early warning based on the fault assessment coefficient of the device.

[0011] Preferably, the data analysis module is communicatively and / or electrically connected to the data acquisition module and the fault diagnosis module respectively.

[0012] Preferably, obtaining the operating data and environmental data of the coal preparation plant electrical equipment includes:

[0013] Real-time collect the operating data and environmental data of the coal preparation plant electrical equipment through data sensors; wherein, the operating data includes: equipment temperature and equipment vibration frequency; the environmental data includes: environmental temperature, environmental humidity and dust concentration.

[0014] Preferably, the training method of the pre-trained temperature prediction model includes:

[0015] Obtain several groups of equipment temperatures of the coal preparation plant electrical equipment and the environmental temperature at the corresponding moments based on the database, and record the output power of the equipment at the corresponding moments;

[0016] Mark the equipment temperature of the coal preparation plant electrical equipment and the environmental temperature at the corresponding moments as temperature data, and obtain several temperature data and the output power of the equipment at the corresponding moments;

[0017] Group several temperature data according to the output power of the equipment, specifically:

[0018] Divide several temperature data with the same output power of the equipment into one group to obtain several groups of temperature data under the same state of equipment output power;

[0019] Obtain several temperature conversion coefficients corresponding to the equipment output power by calculating the ratio of the average value of the equipment temperature to the average value of the environmental temperature in the temperature data under the same state of equipment output power;

[0020] Integrate the equipment temperature, environmental temperature, equipment output power, temperature conversion coefficient corresponding to the equipment output power, and environmental temperature at the prediction moment at the initial moment into standard input data; integrate the equipment temperature at the prediction moment into standard output data;

[0021] Train an artificial intelligence model based on standard input data and standard output data to obtain a temperature prediction model; wherein, the artificial intelligence model includes: a convolutional neural network or a deep belief network.

[0022] It should be noted that the database stores historical data of the operating data and environmental data of the coal preparation plant electrical equipment;

[0023] The initial moment is the current moment specified manually, that is, set the moment corresponding to a certain data in the historical data as the current moment; the prediction moment refers to a future moment after the current moment, which can be set according to actual prediction needs.

[0024] Preferably, the prediction of the operating data of the equipment based on the pre-trained temperature prediction model includes:

[0025] Obtain the environmental temperature at the prediction moment through the weather prediction platform;

[0026] Input the equipment temperature, environmental temperature, equipment output power, temperature conversion coefficient corresponding to the equipment output power at the current moment, and the environmental temperature at the prediction moment into the pre-trained temperature prediction model to obtain the equipment temperature at the prediction moment;

[0027] Update the equipment temperature in the operating data at the current moment collected to the equipment temperature at the prediction moment to obtain the predicted operating data.

[0028] Preferably, the calculation of the target dust deposition rate based on the environmental data includes:

[0029] Obtain a number of dust concentrations and corresponding dust deposition rates under standard environmental temperature and standard environmental humidity based on historical dust data;

[0030] Train an artificial intelligence model based on the training data to obtain a dust deposition rate recognition model; wherein, the training data includes: training input data and training output data; the training input data is the dust concentration, and the training output data is the dust deposition rate corresponding to the dust concentration;

[0031] Input the dust concentration collected in real time into the dust deposition rate recognition model to obtain the corresponding dust deposition rate;

[0032] Obtain the environmental humidity at the prediction moment through the weather prediction platform, and extract the environmental temperature at the prediction moment;

[0033] Take the environmental temperature and environmental humidity at the prediction moment as independent variables, and mark them as T and S respectively; take the corrected dust deposition rate as the dependent variable, and mark it as the target dust deposition rate V;

[0034] Fit the independent variable and the dependent variable by polynomial fitting to construct a correction model;

[0035] The correction model is specifically as follows:

[0036] V = CV×(1 + α1×e^(((T - BT)^2) / BT^2)+α2×e^(((S - BS)^2) / BS^2)); where CV is the dust deposition rate output by the dust deposition rate identification model, BT is the standard temperature, BS is the standard humidity, and α1, α2 are proportionality coefficients;

[0037] For the proportionality coefficient α1: when T - BT < 0, the value range of α1 is (0, 1); when T - BT > 0, the value range of α1 is (-1, 0); when T - BT = 0, α1 = 0;

[0038] For the proportionality coefficient α2: when S - BS < 0, the value range of α2 is (-1, 0); when S - BS > 0, the value range of α2 is (0, 1); when S - BS = 0, α2 = 0;

[0039] Based on the correction model, the dust deposition rate output by the dust deposition rate identification model is corrected to obtain the target dust deposition rate.

[0040] It should be noted that historical dust data refers to the data set of dust concentration and its corresponding dust deposition rate collected and recorded over a long period under specific standard environmental conditions (such as standard temperature and humidity); these data are usually obtained through laboratory or on-site monitoring, reflecting the natural deposition law of dust under different environmental parameters, and are the basis for constructing the dust deposition rate identification model;

[0041] The higher the environmental temperature, the lower the dust deposition rate on the equipment surface usually is; high temperature will enhance air convection and particle Brownian motion, making it difficult for dust to settle; at the same time, if the surface temperature of the equipment is higher than the environmental temperature, the thermophoretic effect will repel particles, further inhibiting deposition; conversely, when the temperature is lower, the air viscosity increases, the particle kinetic energy decreases, and the dust is more likely to deposit, and the dust accumulation thickness increases faster;

[0042] The higher the environmental humidity, the higher the dust deposition rate; high humidity makes dust particles adsorb moisture, forming a liquid bridge force, significantly enhancing the adhesion, resulting in a rapid thickening of the dust accumulation layer; conversely, when the humidity is lower, the dust is dry and loose, the adhesion force weakens, the deposition rate decreases, and the dust accumulation thickness increases slowly.

[0043] Preferably, the correction of the predicted operation data based on the target dust deposition rate includes:

[0044] Correcting the equipment temperature at the prediction moment in the predicted operation data based on the target dust deposition rate, specifically:

[0045] The target device temperature is calculated by the formula W = YW×(1 + β×e^(V / (V + 1))); where W is the target device temperature, YW is the device temperature at the prediction moment, and β is the proportionality coefficient;

[0046] Update the device temperature at the prediction moment in the predicted operation data to the target device temperature to obtain the target operation data.

[0047] It should be noted that the proportionality coefficient β is set by those skilled in the art according to actual experience;

[0048] The main reason why the dust deposition rate directly affects the device temperature is its significant inhibitory effect on heat conduction and heat dissipation efficiency; when dust continuously deposits on the device surface, a dense heat insulation layer will be formed, hindering the effective transfer of heat from the device interior to the external environment; this thermal resistance effect causes the heat generated during the operation of the device to not be dissipated in time, resulting in local overheating and even an increase in the overall temperature; in addition, dust deposition may also block the ventilation channels, restricting air flow and leading to a decline in the cooling effect; therefore, the higher the dust deposition rate, the greater the risk of an increase in the device temperature, and long-term accumulation may even cause device failures or performance degradation.

[0049] Preferably, calculating the device fault evaluation coefficient based on the target operation data includes:

[0050] Extract the target device temperature W and mark the device vibration frequency as Z;

[0051] The device fault evaluation coefficient is calculated by the formula P = θ1×tanh(W)×e^(W / (W + 1)) + θ2×tanh(Z)×e^(Z / (Z + 1)); where P is the device fault evaluation coefficient, and θ1, θ2 are weight coefficients.

[0052] It should be noted that the weight coefficients θ1, θ2 are set by those skilled in the art according to actual experience;

[0053] The device fault evaluation coefficient is used to evaluate the device state at the prediction moment.

[0054] Preferably, judging whether to give an early warning based on the device fault evaluation coefficient includes:

[0055] Judge whether the device fault evaluation coefficient is greater than the preset device fault evaluation coefficient threshold; if so, generate an early warning message and send it to the client; if not, continue to monitor and judge.

[0056] It should be noted that the preset device fault evaluation coefficient threshold is set by those skilled in the art according to actual experience.

[0057] The second aspect of the present invention provides a method for diagnosing electrical equipment faults in a coal preparation plant, including:

[0058] Step 1: Obtain the operation data and environmental data of the coal preparation plant electrical equipment;

[0059] Step 2: Predict the operation data of the equipment based on the pre-trained temperature prediction model to obtain the predicted operation data;

[0060] Step 3: Calculate the target dust deposition rate based on the environmental data;

[0061] Step 4: Correct the predicted operation data based on the target dust deposition rate to obtain the target operation data;

[0062] Step 5: Calculate the fault evaluation coefficient of the equipment based on the target operation data;

[0063] Step 6: Determine whether to give an early warning based on the fault evaluation coefficient of the equipment.

[0064] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0065] The prior art ignores the dynamic interference of dust deposition on the heat conduction path. Dust deposition on the surface of the equipment will form a heat insulation layer, significantly reducing the heat dissipation efficiency. As time goes by, more and more dust will deposit, thus affecting the heat dissipation of the equipment, resulting in a large deviation between the predicted temperature of the equipment in the prior art and the actual temperature. The present invention combines the environmental correction mechanism of the dust deposition rate with the prediction of the equipment operation state. By collecting environmental data and equipment operation data in real time, a two-layer analysis framework including a dust deposition rate correction model and a comprehensive equipment fault evaluation model is constructed. An artificial intelligence model is trained using historical dust data, combined with a non-linear correction function of environmental temperature and humidity, to dynamically calculate the target dust deposition rate. Based on this deposition rate, the output result of the pre-trained temperature prediction model is corrected to eliminate the interference effect of the dust heat insulation layer on heat conduction, significantly improving the accuracy of equipment temperature prediction. By fusing the corrected equipment temperature and vibration frequency, a fault diagnosis model based on dual-parameter weighted evaluation is constructed to realize the intelligent fault early warning from the single physical parameter threshold judgment to the multi-source heterogeneous data-driven. Compared with the prior art, the present invention solves the problem of prediction distortion of the attenuation of the equipment heat dissipation performance caused by dust accumulation by introducing a dust deposition dynamic correction mechanism, and at the same time enhances the robustness of fault identification through multi-parameter joint modeling, greatly reducing the false alarm rate and missed detection rate, providing a more accurate decision-making basis for the predictive maintenance of the coal preparation plant electrical equipment, and effectively improving the equipment operation reliability and safety production level. Description of the Drawings

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

[0067] Figure 1 Schematic diagram of system modules according to an embodiment of the present invention;

[0068] Figure 2 Schematic diagram of the method steps of an embodiment of the present invention. DETAILED DESCRIPTION

[0069] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0070] See also Figure 1 , a first aspect of the present invention provides a coal preparation plant electrical equipment fault diagnosis system, comprising: a data acquisition module, a data analysis module and a fault diagnosis module;

[0071] Data acquisition module: used to obtain operating data and environmental data of electrical equipment in coal preparation plants;

[0072] Data analysis module: predicts the equipment's operating data based on a pre-trained temperature prediction model to obtain predicted operating data; calculates a target dust deposition rate based on environmental data; corrects the predicted operating data based on the target dust deposition rate to obtain target operating data; and,

[0073] Calculate the equipment's fault assessment coefficient based on target operating data;

[0074] Fault diagnosis module: Determines whether to issue an early warning based on the equipment's fault assessment coefficient.

[0075] Obtain operating and environmental data of electrical equipment in coal preparation plants, including:

[0076] Data sensors are used to collect real-time operating data and environmental data of electrical equipment in coal preparation plants. The operating data includes equipment temperature and vibration frequency, while the environmental data includes ambient temperature, humidity, and dust concentration.

[0077] The training method of the pre-trained temperature prediction model includes:

[0078] Obtain the equipment temperatures of several coal preparation plant electrical equipment and the ambient temperatures at corresponding times based on a database, and record the output power of the equipment at the corresponding times;

[0079] Mark the equipment temperatures of the coal preparation plant electrical equipment and the ambient temperatures at corresponding times as temperature data, obtaining several temperature data and the output power of the equipment at the corresponding times;

[0080] Group several temperature data according to the output power of the equipment, specifically:

[0081] Group several temperature data with the same output power of the equipment into one group, obtaining several groups of temperature data under the same state of equipment output power;

[0082] By calculating the ratio of the average value of the equipment temperature to the average value of the ambient temperature in the temperature data under the same state of equipment output power, obtain several temperature conversion coefficients corresponding to the equipment output power;

[0083] Integrate the equipment temperature, ambient temperature, equipment output power, temperature conversion coefficient corresponding to the equipment output power, and ambient temperature at the prediction time at the initial time into standard input data; Integrate the equipment temperature at the prediction time into standard output data;

[0084] Train an artificial intelligence model based on the standard input data and standard output data to obtain a temperature prediction model; Among them, the artificial intelligence model includes: a convolutional neural network or a deep belief network.

[0085] Predict the operation data of the equipment based on the pre-trained temperature prediction model, including:

[0086] Obtain the ambient temperature at the prediction time through a weather prediction platform;

[0087] Input the equipment temperature, ambient temperature, equipment output power, temperature conversion coefficient corresponding to the equipment output power, and ambient temperature at the prediction time at the current time into the pre-trained temperature prediction model to obtain the equipment temperature at the prediction time;

[0088] Update the equipment temperature in the operation data at the currently collected current time to the equipment temperature at the prediction time to obtain predicted operation data.

[0089] Calculate the target dust deposition rate based on environmental data, including:

[0090] Obtain several dust concentrations and the corresponding dust deposition rates under standard ambient temperature and standard ambient humidity based on historical dust data;

[0091] An artificial intelligence model is trained based on training data to obtain a dust deposition rate recognition model; wherein the training data includes: training input data and training output data; the training input data is dust concentration, and the training output data is the dust deposition rate corresponding to the dust concentration;

[0092] By inputting the dust concentration collected in real time into the dust deposition rate identification model, the corresponding dust deposition rate is obtained;

[0093] Obtain the ambient humidity at the forecast time through the weather forecast platform, and extract the ambient temperature at the forecast time;

[0094] The ambient temperature and humidity at the time of prediction are taken as independent variables and marked as T and S respectively; the corrected dust deposition rate is taken as the dependent variable and marked as the target dust deposition rate V;

[0095] Fit the independent variables and dependent variables by polynomial fitting to build a revised model;

[0096] The correction model is specifically:

[0097] V = CV × (1 + α1 × e^(((T-BT)^2) / BT^2) + α2 × e^(((S-BS)^2) / BS^2)); where CV is the dust deposition rate output by the dust deposition rate identification model, BT is the standard temperature, BS is the standard humidity, and α1 and α2 are proportional coefficients;

[0098] For the proportional coefficient α1: when T-BT < 0, the value range of α1 is (0, 1); when T-BT > 0, the value range of α1 is (-1, 0); when T-BT = 0, α1 = 0;

[0099] For the proportional coefficient α2: when S-BS < 0, the value range of α2 is (-1, 0); when S-BS > 0, the value range of α2 is (0, 1); when S-BS = 0, α2 = 0;

[0100] The dust deposition rate output by the dust deposition rate identification model is corrected based on the correction model to obtain the target dust deposition rate.

[0101] Correction of the predicted operating data based on the target dust deposition rate, including:

[0102] The equipment temperature at the predicted time in the predicted operation data is corrected based on the target dust deposition rate, specifically:

[0103] The target device temperature is calculated using the formula W = YW × (1 + β × e^(V / (V+1))) , where W is the target device temperature, YW is the device temperature at the predicted time, and β is the proportionality factor.

[0104] The device temperature at the predicted time in the predicted operation data is updated to the target device temperature to obtain the target operation data.

[0105] The equipment failure assessment coefficient is calculated based on the target operating data, including:

[0106] Extract the target device temperature W and mark the device vibration frequency as Z;

[0107] The equipment failure assessment coefficient is calculated using the formula P = θ1 × tanh(W) × e^(W / (W+1)) + θ2 × tanh(Z) × e^(Z / (Z+1)); where P is the equipment failure assessment coefficient, and θ1 and θ2 are weight coefficients.

[0108] Determine whether to issue an early warning based on the equipment's fault assessment coefficient, including:

[0109] Determine whether the fault assessment coefficient of the device is greater than the preset fault assessment coefficient threshold; if yes, generate an early warning message and send it to the client; if not, continue monitoring and judgment.

[0110] For example, a high-voltage motor (model: YKK560-6, rated power 750kW) in a coal preparation plant has been operating in a high-dust environment for a long time. The details are as follows:

[0111] 1. Data acquisition module;

[0112] Operation data:

[0113] Current time (10:00):

[0114] Equipment temperature: 58°C (real-time acquisition via infrared thermal imager).

[0115] Vibration frequency: 6.2Hz (monitored by vibration sensor).

[0116] Prediction time (12:00):

[0117] The ambient temperature obtained through the weather platform is: 32℃ (high temperature warning).

[0118] Environmental data:

[0119] Current ambient temperature: 28°C (humidity: 65% RH).

[0120] Real-time dust concentration: 420mg / m 3 (Collected by laser dust sensor).

[0121] 2. Data analysis module;

[0122] (1) Temperature prediction model prediction;

[0123] Training data:

[0124] Historical data in the database: When the motor output power is 750kW, the ratio of the average equipment temperature to the average ambient temperature is 1.35 (i.e., the temperature conversion coefficient).

[0125] Input data:

[0126] Initial equipment temperature: 58°C, ambient temperature: 28°C, output power: 750kW, temperature conversion coefficient: 1.35, ambient temperature at the predicted time: 32°C.

[0127] Prediction results:

[0128] Calculated by the convolutional neural network model (CNN), the device temperature at the predicted moment is 69°C (uncorrected value).

[0129] (2) Calculation of target dust deposition rate;

[0130] Historical dust data:

[0131] At standard temperature (BT=20℃) and standard humidity (BS=50%), the dust concentration is 420mg / m 3 The corresponding deposition rate is 0.6 mm / h (laboratory calibration data).

[0132] Corrected model calculation:

[0133] The ambient temperature is T = 28°C (T-BT = 8°C > 0), the value range of α1 is (-1, 0), and α1 = -0.25.

[0134] The ambient humidity S = 65% (S-BS = 15% > 0), the value range of α2 is (0, 1), and α2 = 0.35.

[0135] Corrected model formula:

[0136] V=CV×(1+α1×e^(((T-BT)^2) / BT^2)+α2×e^(((S-BS)^2) / BS^2));

[0137] Substituting the data, we get V≈0.665mm / h

[0138] Target dust deposition rate: 0.665 mm / h (considering high temperature inhibition of deposition, the corrected rate is slightly higher than the standard value).

[0139] (3) Correct the predicted equipment temperature;

[0140] Correction formula: W = YW × (1 + β × e^(V / (V+1)));

[0141] The proportionality coefficient β = 0.15 (set according to experience).

[0142] Substituting the data gives W ≈ 83.5 °C.

[0143] Target device temperature: 83.5 °C (the corrected value, significantly higher than the uncorrected 69 °C).

[0144] 3. Fault assessment and early warning;

[0145] Extract parameters:

[0146] The target device temperature W = 83.5 °C, and the vibration frequency Z = 6.2 Hz.

[0147] Weight coefficients: θ1 = 0.7 (higher temperature weight), θ2 = 0.3.

[0148] Calculate the equipment fault assessment coefficient through the formula P = θ1 × tanh(W) × e^(W / (W + 1)) + θ2 × tanh(Z) × e^(Z / (Z + 1));

[0149] Substituting the data gives: P ≈ 1.074.

[0150] Fault assessment coefficient: 1.074 (higher than the preset threshold of 0.8).

[0151] Early warning trigger:

[0152] The system generates an early warning message (such as "High risk of motor overheating, it is recommended to immediately check the cooling system") and sends it to the mobile phone of the operation and maintenance personnel through the client.

[0153] In this example, by dynamically correcting the dust deposition rate, the abnormal temperature of the motor is accurately predicted, and an early warning is triggered based on the multi-parameter fusion evaluation, avoiding the risk of equipment damage and shutdown caused by high temperature. This method has significant practical application value in the high-dust environment of coal preparation plants.

[0154] Refer to Figure 2 , the second aspect embodiment of the present invention provides a method for diagnosing faults in electrical equipment of a coal preparation plant, including:

[0155] Step 1: Obtain the operation data and environmental data of the electrical equipment in the coal preparation plant;

[0156] Step 2: Predict the operation data of the equipment based on a pre-trained temperature prediction model to obtain predicted operation data;

[0157] Step 3: Calculate the target dust deposition rate based on the environmental data;

[0158] Step 4: Correct the predicted operation data based on the target dust deposition rate to obtain the target operation data;

[0159] Step 5: Calculate the equipment's fault assessment coefficient based on the target operating data;

[0160] Step 6: Determine whether to issue an early warning based on the equipment's fault assessment coefficient.

[0161] Some of the data in the above formula are calculated by removing the dimensions and taking their numerical values. The formula is a formula that is closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0162] The above embodiments are only used to illustrate the technical method of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A coal preparation plant electrical equipment fault diagnosis system, characterized in that, Including: A data acquisition module, a data analysis module, and a fault diagnosis module; The data acquisition module: used to obtain the operation data of the electrical equipment in the coal preparation plant and the environmental data; The data analysis module: based on a pre-trained temperature prediction model, predicts the operation data of the equipment to obtain predicted operation data; Calculates the target dust deposition rate based on the environmental data; Corrects the predicted operation data based on the target dust deposition rate to obtain the target operation data; and, Calculates the fault evaluation coefficient of the equipment based on the target operation data; The fault diagnosis module: determines whether to give an early warning based on the fault evaluation coefficient of the equipment.

2. The coal preparation plant electrical equipment fault diagnosis system according to claim 1, characterized in that, The data analysis module is communicatively and / or electrically connected to the data acquisition module and the fault diagnosis module respectively.

3. The coal preparation plant electrical equipment fault diagnosis system according to claim 1, characterized in that, The obtaining of the operation data of the electrical equipment in the coal preparation plant and the environmental data includes: Real-time collecting the operation data of the electrical equipment in the coal preparation plant and the environmental data through data sensors; wherein, the operation data includes: equipment temperature and equipment vibration frequency; the environmental data includes: environmental temperature, environmental humidity, and dust concentration.

4. The coal preparation plant electrical equipment fault diagnosis system according to claim 1, characterized in that, The training method of the pre-trained temperature prediction model includes: Based on a database, obtaining a number of equipment temperatures of the electrical equipment in the coal preparation plant and the environmental temperatures at corresponding times, and recording the output power of the equipment at the corresponding times; Marking the equipment temperature of the electrical equipment in the coal preparation plant and the environmental temperature at the corresponding time as temperature data, obtaining a number of temperature data and the output power of the equipment at the corresponding times; Grouping the number of temperature data according to the output power of the equipment, specifically: Dividing a number of temperature data with the same output power of the equipment into one group, obtaining a number of groups of temperature data in the state of the same equipment output power; By calculating the ratio of the average value of the equipment temperature to the average value of the environmental temperature in the temperature data in the state of the same equipment output power, obtaining a number of temperature conversion coefficients corresponding to the equipment output power; Integrating the equipment temperature, environmental temperature, equipment output power, temperature conversion coefficient corresponding to the equipment output power, and environmental temperature at the prediction time at the initial time into standard input data; integrating the equipment temperature at the prediction time into standard output data; Training an artificial intelligence model based on the standard input data and the standard output data to obtain a temperature prediction model; wherein, the artificial intelligence model includes: a convolutional neural network or a deep belief network.

5. The coal preparation plant electrical equipment fault diagnosis system according to claim 1, characterized in that, The predicting of the operation data of the equipment based on the pre-trained temperature prediction model includes: Obtaining the environmental temperature at the prediction time through a weather prediction platform; Inputting the equipment temperature, environmental temperature, equipment output power, temperature conversion coefficient corresponding to the equipment output power, and environmental temperature at the current time into the pre-trained temperature prediction model to obtain the equipment temperature at the prediction time; Updating the equipment temperature in the operation data collected at the current time to the equipment temperature at the prediction time to obtain the predicted operation data.

6. The coal preparation plant electrical equipment fault diagnosis system according to claim 1, characterized in that, The calculating of the target dust deposition rate based on the environmental data includes: Based on historical dust data, obtaining a number of dust concentrations and the corresponding dust deposition rates under standard environmental temperature and standard environmental humidity; Train an artificial intelligence model based on training data to obtain a dust deposition rate identification model; wherein, the training data includes: training input data and training output data; the training input data is the dust concentration, and the training output data is the dust deposition rate corresponding to the dust concentration; Input the dust concentration obtained by real-time acquisition into the dust deposition rate identification model to obtain the corresponding dust deposition rate; Obtain the environmental humidity at the prediction moment through the weather prediction platform, and extract the environmental temperature at the prediction moment; Take the environmental temperature and environmental humidity at the prediction moment as independent variables, and mark them as T and S respectively; take the corrected dust deposition rate as the dependent variable, and mark it as the target dust deposition rate V; Fit the independent variable and the dependent variable by polynomial fitting to construct a correction model; The correction model is specifically: V = CV×(1 + α1×e^(((T - BT)^2) / BT^2) + α2×e^(((S - BS)^2) / BS^2)); where, CV is the dust deposition rate output by the dust deposition rate identification model, BT is the standard temperature, BS is the standard humidity, and α1, α2 are proportionality coefficients; For the proportionality coefficient α1: when T - BT < 0, the value range of α1 is (0, 1); when T - BT > 0, the value range of α1 is (-1, 0); when T - BT = 0, α1 = 0; For the proportionality coefficient α2: when S - BS < 0, the value range of α2 is (-1, 0); when S - BS > 0, the value range of α2 is (0, 1); when S - BS = 0, α2 = 0; Based on the correction model, correct the dust deposition rate output by the dust deposition rate identification model to obtain the target dust deposition rate.

7. The coal preparation plant electrical equipment fault diagnosis system according to claim 6, characterized in that, The correction of the predicted operation data based on the target dust deposition rate includes: Correct the equipment temperature at the prediction moment in the predicted operation data based on the target dust deposition rate, specifically: Calculate the target equipment temperature through the formula W = YW×(1 + β×e^(V / (V + 1))); where, W is the target equipment temperature, YW is the equipment temperature at the prediction moment, and β is the proportionality coefficient; Update the equipment temperature at the prediction moment in the predicted operation data to the target equipment temperature to obtain the target operation data.

8. The coal preparation plant electrical equipment fault diagnosis system according to claim 1, characterized in that, The calculation of the equipment failure evaluation coefficient based on the target operation data includes: Extract the target equipment temperature W, and mark the equipment vibration frequency as Z; Calculate the equipment failure evaluation coefficient through the formula P = θ1×tanh(W)×e^(W / (W + 1)) + θ2×tanh(Z)×e^(Z / (Z + 1)); where, P is the equipment failure evaluation coefficient, and θ1, θ2 are weight coefficients.

9. The coal preparation plant electrical equipment fault diagnosis system according to claim 1, characterized in that The judgment of whether to give an early warning based on the equipment failure evaluation coefficient includes: Judge whether the equipment failure evaluation coefficient is greater than the preset equipment failure evaluation coefficient threshold; if yes, generate an early warning message and send it to the client; if no, continue to monitor and judge.

10. A method for diagnosing faults in electrical equipment of a coal preparation plant, which is applied to a fault diagnosis system for electrical equipment of a coal preparation plant according to any one of claims 1-9, characterized in that, Include: Step 1: Obtain the operation data and environmental data of the coal preparation plant electrical equipment; Step 2: Predict the operation data of the equipment based on the pre-trained temperature prediction model to obtain the predicted operation data; Step 3: Calculate the target dust deposition rate based on the environmental data; Step 4: Correct the predicted operation data based on the target dust deposition rate to obtain the target operation data; Step 5: Calculate the fault assessment coefficient of the equipment based on the target operation data; Step 6: Determine whether to give an early warning based on the fault assessment coefficient of the equipment.

Images